AI RESEARCH
Comparative Analysis of Patch Attack on VLM-Based Autonomous Driving Architectures
arXiv CS.CV
•
ArXi:2603.08897v1 Announce Type: new Vision-language models are emerging for autonomous driving, yet their robustness to physical adversarial attacks remains unexplored. This paper presents a systematic framework for comparative adversarial evaluation across three VLM architectures: Dolphins, OmniDrive (Omni-L), and LeapVAD. Using black-box optimization with semantic homogenization for fair comparison, we evaluate physically realizable patch attacks in CARLA simulation.